cs.LG(2024-02-15)

📊 共 24 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (17) 支柱九:具身大模型 (Embodied Foundation Models) (7 🔗1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (17 篇)

#题目一句话要点标签🔗
1 Smart Information Exchange for Unsupervised Federated Learning via Reinforcement Learning 提出基于强化学习的智能信息交换以解决无监督联邦学习问题 reinforcement learning
2 Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment 提出Rewards-in-Context以解决多目标对齐问题 reinforcement learning large language model foundation model
3 Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning 提出通用黑箱奖励中毒攻击以解决离线强化学习安全问题 reinforcement learning offline RL offline reinforcement learning
4 Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts 提出风险敏感的软演员评论家以应对分布变化问题 reinforcement learning deep reinforcement learning
5 Enhancing Courier Scheduling in Crowdsourced Last-Mile Delivery through Dynamic Shift Extensions: A Deep Reinforcement Learning Approach 通过动态班次延长提升众包最后一公里配送调度效率 reinforcement learning deep reinforcement learning
6 Reward Generalization in RLHF: A Topological Perspective 提出奖励泛化理论以解决RLHF中的数据效率问题 reinforcement learning preference learning RLHF
7 Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling 提出层次状态空间模型以解决连续序列预测问题 Mamba state space model
8 Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation 提出自我对弈微调方法以提升扩散模型的文本到图像生成能力 reinforcement learning RLHF large language model
9 Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization 提出基于策略优化的RLHF算法以提高数据利用效率 reinforcement learning RLHF
10 Interpretable Imitation Learning via Generative Adversarial STL Inference and Control 提出基于生成对抗网络的可解释模仿学习方法以解决任务理解问题 imitation learning
11 Large Scale Constrained Clustering With Reinforcement Learning 提出基于强化学习的约束聚类方法以解决资源分配问题 reinforcement learning
12 $f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning 提出$f$-MICL以解决InfoNCE对比学习的局限性 contrastive learning
13 Non-orthogonal Age-Optimal Information Dissemination in Vehicular Networks: A Meta Multi-Objective Reinforcement Learning Approach 提出一种元多目标强化学习方法以优化车载网络中的信息传播 reinforcement learning
14 Recurrent Reinforcement Learning with Memoroids 提出Memoroids框架以提升递归强化学习的样本效率 reinforcement learning
15 Performative Reinforcement Learning in Gradually Shifting Environments 提出渐变环境下的表演强化学习框架以解决动态变化问题 reinforcement learning
16 Knowledge-guided EEG Representation Learning 提出知识引导的自监督学习模型以提升EEG信号分析 representation learning
17 Discrete Probabilistic Inference as Control in Multi-path Environments 提出生成流网络以解决多路径环境中的离散概率推断问题 reinforcement learning flow matching

🔬 支柱九:具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗
18 Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review 系统评估大语言模型在预测与异常检测中的应用与挑战 large language model multimodal
19 Generative AI and Process Systems Engineering: The Next Frontier 探讨生成性人工智能在过程系统工程中的应用与挑战 large language model foundation model
20 SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention 提出SAMformer以解决多变量时间序列预测中的局部最优问题 foundation model
21 BitDelta: Your Fine-Tune May Only Be Worth One Bit 提出BitDelta以降低微调模型的存储需求 large language model
22 QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference 提出QUICK以解决量化大语言模型推理效率问题 large language model
23 All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretraining 提出GCOPE以解决跨领域图预训练中的负迁移问题 large language model
24 How to Train Data-Efficient LLMs 提出数据高效的LLM训练方法以降低资源消耗 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页